{"id":"W4402305984","doi":"10.1016/j.ifacol.2024.08.357","title":"Sensitivity-based Adaptive Sampling for Physics-Informed Neural Networks","year":2024,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sensitivity (control systems); Artificial neural network; Adaptive sampling; Sampling (signal processing); Computer science; Artificial intelligence; Statistical physics; Physics; Psychology; Mathematics; Engineering; Electronic engineering; Statistics; Telecommunications; Monte Carlo method","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001281097,0.0002889895,0.0002757949,0.00004986547,0.0002002256,0.0001309123,0.00008375206,0.00007292334,0.000137612],"category_scores_gemma":[0.000005926757,0.0002562895,0.0003412821,0.0002382992,0.00006267938,0.0002184578,0.00002887043,0.0003550051,0.00001970908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004307493,"about_ca_system_score_gemma":0.00009466903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000042726,"about_ca_topic_score_gemma":0.00001134085,"domain_scores_codex":[0.9986849,0.00003667353,0.000245826,0.0004143632,0.000151245,0.0004669326],"domain_scores_gemma":[0.9991072,0.000421491,0.00006494522,0.000192942,0.00007385177,0.0001395307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000207246,0.0001235521,0.0002342099,0.00006037169,0.0001908458,0.000008265812,0.0002143256,0.6601745,0.001033843,0.01281638,0.0002773258,0.3246592],"study_design_scores_gemma":[0.0004705973,0.00008147053,0.00003207283,0.00007465082,0.00006026,0.000002303816,0.0001478381,0.9951947,0.0004908459,0.0004800856,0.002671016,0.0002941764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03371691,0.0001737824,0.9616809,0.001195926,0.001317529,0.0005254296,0.0002268419,0.0002597155,0.0009028877],"genre_scores_gemma":[0.939746,0.000004038656,0.05421163,0.0004583783,0.004394833,0.00006737014,0.0004727998,0.0000574757,0.0005874428],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9074693,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04262099501472316,"score_gpt":0.304828750572557,"score_spread":0.2622077555578338,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}